© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86217
    Prev
    Next
    INDEX
    Explanations

    bolded list headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     logarith
    0.41
     illogical
    0.40
    <0x8F>
    0.38
    ഫ്
    0.38
    लं
    0.38
     parametric
    0.38
    Swedish
    0.38
    ))->
    0.38
    विद्या
    0.37
    ಫ್
    0.37
    POSITIVE LOGITS
     あなた
    0.43
     κάπο
    0.43
    あなた
    0.42
     पहना
    0.39
     কোনটা
    0.39
     peste
    0.39
    どれ
    0.38
    絆
    0.38
    쐞
    0.37
     Körper
    0.36
    Activations Density 0.019%

    No Known Activations